Early-February flotsam

[This article was first published on Quantum Forest » rblogs, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Mike Croucher at Walking Randomly points out an interesting difference in operator precedence for several mathematical packages to evaluate a simple operation 2^3^4. It is pretty much a divide between Matlab and Excel (does the later qualify as mathematical software?) on one side with result 4096 (or (2^3)^4) and Mathematica, R and Python on the other, resulting on 2417851639229258349412352 (or 2^(3^4)). Remember your parentheses…

Corey Chivers, aka Bayesian Biologist, uses R to help students understand the Monty Hall problem. I think a large part of the confusion to grok it stems from a convenient distraction: opening doors. The problem could be reframed as: i- you pick a door (so probability of winning the prize is 1/3) and Monty gets the other two doors (probability of winning is 2/3), ii- Monty is offering to switch all his doors for yours, so switching increases the probability of winning, iii- Monty will never open a winning door to entice the switch, so we should forget about them.

To make the point clearer, let’s imagine now that instead of 3 doors the game has 10 doors. You pick one (probability of winning 1/10) and Monty keeps 9 (probability of winning 9/10). Would you switch one door for nine? Of course! The fact that Monty will open 8 non-winning doors rather than all of his doors does not make a difference in the deal.

# Number of games and doors
n.games = 10000
n.doors = 10

# Assign prize to door for each game. Remember:
# Monty keeps all doors not chosen by player
prize.door = floor(runif(n.games, 1, n.doors + 1))
player.door = floor(runif(n.games, 1, n.doors + 1))

# If prize.door and player.door are the same
# and player does not switch
are.same = prize.door == player.door
cat('Probability of winning by not switching', sum(are.same)/n.games, '\n')
cat('Probability of winning by switching', (n.games - sum(are.same))/n.games, '\n')

Gratuitous picture: fish in New Brighton pier (Photo: Luis).

Pierre Lemieux reminds us that “a dishonest statistician is an outliar”.

If you want to make dulce de leche using condensed milk—but lack a pressure cooker—use an autoclave for 50 to 60 minutes. HT: Heidi Smith.

Lesser and Pearl remind us that there are at least 20 modalities for making statistics fun in “Functional Fun in Statistics Teaching: Resources, Research and Recommendations”. HT: Chelsea Heaven.

An old review of Buddhism without Beliefs: A Contemporary Guide to Awakening by Stephen Batchelor. I can’t see any statistical angle, but I liked that book.

Back to quantitative genetics!

To leave a comment for the author, please follow the link and comment on their blog: Quantum Forest » rblogs.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)